Confirm the source
Compare the repository, publisher, and installation command before continuing.
×
Third-party audit
High riskGen Agent Trust Hub
firecrawl-website-design-clone · firecrawl/firecrawl-workflows
Provider summary
This skill is generally functional but contains a significant security risk regarding how it handles user input. It recommends executing shell commands using URLs provided by users, which can lead to command injection. Additionally, it processes untrusted website content to generate instructions for other AI agents, creating a surface for indirect prompt injection.
The provider classified the analyzed snapshot as HIGH risk. This result applies to the content available at audit time.
- Provider
- Gen Agent Trust Hub
- Normalized result
- fail
- Risk level
- HIGH
- Audited
- May 17, 2026
How to use this signal
Read the content
Review SKILL.md, scripts, and allowed tools. OpenAI Suite never executes them during indexing.
Limit permissions
Use the narrowest possible scope and avoid broad credentials for third-party skills.